{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OGQRKVTXCMXA5P6SPMXEF64UEQ","short_pith_number":"pith:OGQRKVTX","canonical_record":{"source":{"id":"1705.03562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-09T22:59:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76045a054d08171adf5b981ff1146d89a289237449605df06793aeebc9bcc5f5","abstract_canon_sha256":"7e0c8e505051b153f5062e65c3c37f600ccbf5ab9a68001924a4e7686f11aba9"},"schema_version":"1.0"},"canonical_sha256":"71a1155677132e0ebfd27b2e42fb942411264cac9685378febc7da20ad8f0554","source":{"kind":"arxiv","id":"1705.03562","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03562","created_at":"2026-05-18T00:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03562v1","created_at":"2026-05-18T00:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03562","created_at":"2026-05-18T00:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"OGQRKVTXCMXA","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OGQRKVTXCMXA5P6S","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OGQRKVTX","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OGQRKVTXCMXA5P6SPMXEF64UEQ","target":"record","payload":{"canonical_record":{"source":{"id":"1705.03562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-09T22:59:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76045a054d08171adf5b981ff1146d89a289237449605df06793aeebc9bcc5f5","abstract_canon_sha256":"7e0c8e505051b153f5062e65c3c37f600ccbf5ab9a68001924a4e7686f11aba9"},"schema_version":"1.0"},"canonical_sha256":"71a1155677132e0ebfd27b2e42fb942411264cac9685378febc7da20ad8f0554","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:43.587544Z","signature_b64":"ALvgrEwnJXoPNGZGnbwLvInqvsdIECSu0CpcpItsdelxXSxK2wi4Rb16/nP2mqfJgwbaIWC/enjbP6eIPhA7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71a1155677132e0ebfd27b2e42fb942411264cac9685378febc7da20ad8f0554","last_reissued_at":"2026-05-18T00:44:43.587081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:43.587081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.03562","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uxaEeWxeE193b/mYtY56cPq9NA6Qi83IZ4pRDQa71hyV6uOvwboUNPfyf1unNPNO0Au9DPD5566L5Tmg5FrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:37:06.966804Z"},"content_sha256":"6153dd4c6d412b04a2851959731c6df2817c7283c16f807a977d1c0d6f43ba07","schema_version":"1.0","event_id":"sha256:6153dd4c6d412b04a2851959731c6df2817c7283c16f807a977d1c0d6f43ba07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OGQRKVTXCMXA5P6SPMXEF64UEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Episodic Value Iteration for Model-based Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Steven Stenberg Hansen","submitted_at":"2017-05-09T22:59:18Z","abstract_excerpt":"We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the model-free Q-learning objective, we show that DEVI's model-based internal structure provides `one-shot' transfer to changes in reward and transition structure, even for tasks with very high-dimensional state spaces."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03562","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9iOJCgPTm+Xv3o+QO3gUl4wBeYueUT9pQIx2kJiNhuthDn7b6lwS3n1unWmTO8OhHXqrbNOWA7/TFsReimGxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:37:06.967136Z"},"content_sha256":"50aa53be1222b952358e4adcb89b58b744fb430bb8728abcbd29d42ff00bca06","schema_version":"1.0","event_id":"sha256:50aa53be1222b952358e4adcb89b58b744fb430bb8728abcbd29d42ff00bca06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OGQRKVTXCMXA5P6SPMXEF64UEQ/bundle.json","state_url":"https://pith.science/pith/OGQRKVTXCMXA5P6SPMXEF64UEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OGQRKVTXCMXA5P6SPMXEF64UEQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T15:37:06Z","links":{"resolver":"https://pith.science/pith/OGQRKVTXCMXA5P6SPMXEF64UEQ","bundle":"https://pith.science/pith/OGQRKVTXCMXA5P6SPMXEF64UEQ/bundle.json","state":"https://pith.science/pith/OGQRKVTXCMXA5P6SPMXEF64UEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OGQRKVTXCMXA5P6SPMXEF64UEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OGQRKVTXCMXA5P6SPMXEF64UEQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7e0c8e505051b153f5062e65c3c37f600ccbf5ab9a68001924a4e7686f11aba9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-09T22:59:18Z","title_canon_sha256":"76045a054d08171adf5b981ff1146d89a289237449605df06793aeebc9bcc5f5"},"schema_version":"1.0","source":{"id":"1705.03562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03562","created_at":"2026-05-18T00:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03562v1","created_at":"2026-05-18T00:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03562","created_at":"2026-05-18T00:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"OGQRKVTXCMXA","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OGQRKVTXCMXA5P6S","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OGQRKVTX","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:50aa53be1222b952358e4adcb89b58b744fb430bb8728abcbd29d42ff00bca06","target":"graph","created_at":"2026-05-18T00:44:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the model-free Q-learning objective, we show that DEVI's model-based internal structure provides `one-shot' transfer to changes in reward and transition structure, even for tasks with very high-dimensional state spaces.","authors_text":"Steven Stenberg Hansen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-09T22:59:18Z","title":"Deep Episodic Value Iteration for Model-based Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03562","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6153dd4c6d412b04a2851959731c6df2817c7283c16f807a977d1c0d6f43ba07","target":"record","created_at":"2026-05-18T00:44:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7e0c8e505051b153f5062e65c3c37f600ccbf5ab9a68001924a4e7686f11aba9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-09T22:59:18Z","title_canon_sha256":"76045a054d08171adf5b981ff1146d89a289237449605df06793aeebc9bcc5f5"},"schema_version":"1.0","source":{"id":"1705.03562","kind":"arxiv","version":1}},"canonical_sha256":"71a1155677132e0ebfd27b2e42fb942411264cac9685378febc7da20ad8f0554","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71a1155677132e0ebfd27b2e42fb942411264cac9685378febc7da20ad8f0554","first_computed_at":"2026-05-18T00:44:43.587081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:43.587081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ALvgrEwnJXoPNGZGnbwLvInqvsdIECSu0CpcpItsdelxXSxK2wi4Rb16/nP2mqfJgwbaIWC/enjbP6eIPhA7Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:43.587544Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.03562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6153dd4c6d412b04a2851959731c6df2817c7283c16f807a977d1c0d6f43ba07","sha256:50aa53be1222b952358e4adcb89b58b744fb430bb8728abcbd29d42ff00bca06"],"state_sha256":"d09a61886c3c54d226e62f63ff69cb28b89d9142a81bce98c66ad9849fc43cf8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tm1EReZ0FSGvgyGGMtCUmfO8mWjlDN58BJqQQ14Md5IdJK8KyHqj0aFHgwKnj+W5aMA91Znwktxgisk/srvpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T15:37:06.968925Z","bundle_sha256":"4618f4e1dd517044c73e02053df16572697c65569046c32ffef8779c74faddc8"}}